Firecrawl MCP

Web scraping built for LLMs: turn any site into clean markdown, crawl whole domains, search, and extract structured data.

Category: Search · Works with: Claude Code, Grok Build, Claude Desktop, Cursor, VS Code

What it does

Heavy-duty web ingestion — where the fetch server reads one page, Firecrawl crawls sites, handles JS rendering, and returns structured results. Free tier available.

Install

npx -y firecrawl-mcp

Setup Instructions

claude Code

claude mcp add firecrawl --env FIRECRAWL_API_KEY=fc-YOUR_KEY -- npx -y firecrawl-mcp

cursor

Get an API key at firecrawl.dev, then add the server with FIRECRAWL_API_KEY in its env block.

Official documentation

Compatible Agents

Claude CodeGrok BuildClaude DesktopCursorVS Code

Related MCP Servers

@modelcontextprotocol/server-filesystem

Reference filesystem access for agents. Read, write, list, move, and search files within explicitly allowed directories.

GitHub MCP Server

GitHub's official MCP server. Manage issues, PRs, branches, workflows, and code scanning — or just let the agent read your repos.

mcp-server-git

Reference Git server. Status, diff, log, branch, commit, and search — structured Git operations for repos the agent works in.